The effect of high ethanol concentration on E-nose response for diabetes detection in exhaled breath: Laboratory studies

Abstract

The growing number of people with diabetes has paved the way for the creation of non-invasive devices to measure blood glucose levels and enable the detection of diabetes non-invasively, for example, through exhaled air. This paper presents the development of a breath detection system using multiple sensors (e-nose system) for the non-invasive estimation of blood glucose levels. The system employs commercially available ethanol, CO2, and acetone sensors, with synthetic breath mixtures used for testing, including four scenarios with high ethanol concentrations (0–570 ppm) as an influence factor. Results showed a mean absolute error of 0.245 ppm when analysing commonly observed acetone concentrations in diabetic breath using four sensors and the XGBoost Regressor. In mixtures with high ethanol concentrations and varying acetone concentrations (0–8.62 ppm), the CatBoost Regressor outperformed other machine learning algorithms with a mean absolute error of 0.568 ppm. This study emphasises the significant impact of ethanol on acetone detection and the need to consider ethanol levels in the developing of non-invasive devices for blood glucose prediction based on the exhaled acetone measurements. The research shows that a set of three gas sensors is optimal for estimating acetone concentrations in gas mixtures. The presented results constitute a preliminary step towards developing a non-invasive device for estimating blood glucose levels based on breath analysis, with the novelty of considering alcohol intake as a potential influencing factor.